Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    иг

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <td
    -0.07
    แพร
    -0.07
    .useState
    -0.07
     Joanna
    -0.06
     bulbs
    -0.06
     tạp
    -0.06
    bf
    -0.06
    Defaults
    -0.06
     Availability
    -0.06
     absent
    -0.06
    POSITIVE LOGITS
    σι
    0.08
     integer
    0.07
     nông
    0.07
     систем
    0.07
    ژ
    0.06
    gae
    0.06
    .Shape
    0.06
     unleashed
    0.06
    τρ
    0.06
    (NUM
    0.06
    Act Density 0.002%

    No Known Activations